no code implementations • 14 Feb 2024 • Alexandre Chenu, Olivier Serris, Olivier Sigaud, Nicolas Perrin-Gilbert
Demonstrations are commonly used to speed up the learning process of Deep Reinforcement Learning algorithms.
1 code implementation • 9 Nov 2022 • Alexandre Chenu, Olivier Serris, Olivier Sigaud, Nicolas Perrin-Gilbert
This sequential goal-reaching approach raises a problem of compatibility between successive goals: we need to ensure that the state resulting from reaching a goal is compatible with the achievement of the following goals.
1 code implementation • 15 Apr 2022 • Alexandre Chenu, Nicolas Perrin-Gilbert, Olivier Sigaud
In such context, Imitation Learning (IL) can be a powerful approach to bootstrap the learning process.
no code implementations • 10 Apr 2021 • Alexandre Chenu, Nicolas Perrin-Gilbert, Stéphane Doncieux, Olivier Sigaud
In particular, we show empirically that, if the mapping is smooth enough, i. e. if two close policies in the parameter space lead to similar outcomes, then diversity algorithms tend to inherit exploration properties of MP algorithms.